Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection

In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised object detection (SSOD). Our core observation is that the oscillating pseudo-targets undermine the training of an accurate detector. It injects noise into the student's training, leading to severe overfitting problems. Therefore, we propose a systematic solution, termed ConsistentTeacher, to reduce the inconsistency. First, adaptive anchor assignment~(ASA) substitutes the static IoU-based strategy, which enables the student network to be resistant to noisy pseudo-bounding boxes. Then we calibrate the subtask predictions by designing a 3D feature alignment module~(FAM-3D). It allows each classification feature to adaptively query the optimal feature vector for the regression task at arbitrary scales and locations. Lastly, a Gaussian Mixture Model (GMM) dynamically revises the score threshold of pseudo-bboxes, which stabilizes the number of ground truths at an early stage and remedies the unreliable supervision signal during training. ConsistentTeacher provides strong results on a large range of SSOD evaluations. It achieves 40.0 mAP with ResNet-50 backbone given only 10% of annotated MS-COCO data, which surpasses previous baselines using pseudo labels by around 3 mAP. When trained on fully annotated MS-COCO with additional unlabeled data, the performance further increases to 47.7 mAP. Our code is available at \url{}.

PDF Abstract CVPR 2023 PDF CVPR 2023 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semi-Supervised Object Detection COCO 100% labeled data Consistent-Teacher mAP 48.20 # 3
Semi-Supervised Object Detection COCO 10% labeled data Consistent-Teacher mAP 40.0 # 3
detector RetinaNet-Res50 # 1
Semi-Supervised Object Detection COCO 1% labeled data Consistent-Teacher mAP 25.5 # 5
Semi-Supervised Object Detection COCO 2% labeled data Consistent-Teacher mAP 30.7 # 2


No methods listed for this paper. Add relevant methods here